BlenderProc

10/25/2019
by   Maximilian Denninger, et al.
0

BlenderProc is a modular procedural pipeline, which helps in generating real looking images for the training of convolutional neural networks. These can be used in a variety of use cases including segmentation, depth, normal and pose estimation and many others. A key feature of our extension of blender is the simple to use modular pipeline, which was designed to be easily extendable. By offering standard modules, which cover a variety of scenarios, we provide a starting point on which new modules can be created.

READ FULL TEXT
research
12/21/2015

Car Segmentation and Pose Estimation using 3D Object Models

Image segmentation and 3D pose estimation are two key cogs in any algori...
research
12/29/2018

3D Convolution on RGB-D Point Clouds for Accurate Model-free Object Pose Estimation

The conventional pose estimation of a 3D object usually requires the kno...
research
12/29/2016

Computing in quotients of rings of integers

We develop algorithms to turn quotients of rings of rings of integers in...
research
06/21/2021

Segmentation of cell-level anomalies in electroluminescence images of photovoltaic modules

In the operation maintenance (O M) of photovoltaic (PV) plants, th...
research
04/29/2023

CARLA-BSP: a simulated dataset with pedestrians

We present a sample dataset featuring pedestrians generated using the AR...
research
10/28/2022

Learning Modular Simulations for Homogeneous Systems

Complex systems are often decomposed into modular subsystems for enginee...
research
11/06/2020

Toward an Automated HPC Pipeline for Processing Large Scale Electron Microscopy Data

We present a fully modular and scalable software pipeline for processing...

Please sign up or login with your details

Forgot password? Click here to reset